moscot.problems.generic.GWProblem.prepare

GWProblem.prepare(key, x_attr, y_attr, joint_attr=None, policy='sequential', cost='sq_euclidean', cost_kwargs=mappingproxy({}), a=None, b=None, **kwargs)

Prepare the individual quadratic subproblems.

See also

• TODO(michalk8): add an example how to pass x_attr/y_attr.

Parameters:

• key (str) – Key in obs for the SubsetPolicy.

• x_attr (Union[str, Mapping[str, Any]]) –

  How to get the data for the source quadratic term:

  • str - a key in obsm where the data is stored.

  • dict- it should contain 'attr' and 'key', the attribute and key in AnnData, and optionally 'tag' from the tags.

  By default, tag = 'point_cloud' is used.

• y_attr (Union[str, Mapping[str, Any]]) –

  How to get the data for the target quadratic term:

  • str - a key in obsm where the data is stored.

  • dict- it should contain 'attr' and 'key', the attribute and the key in AnnData, and optionally 'tag', one of Tag.

  By default, tag = 'point_cloud' is used.

• joint_attr (Union[str, Mapping[str, Any], None]) –

  How to get the data for the linear term in the fused case:

  • None - run PCA on X is computed.

  • str - a key in obsm where the data is stored.

  • dict- it should contain 'attr' and 'key', the attribute and the key in AnnData, and optionally 'tag', one of Tag.

  By default, tag = 'point_cloud' is used.

• policy (Literal['sequential', 'explicit', 'star']) –

  Rule which defines how to construct the subproblems. Valid options are:

  • 'sequential' - align subsequent categories in obs[{'{key}'].

  • 'explicit' - explicit sequence of subsets passed via subset = [(b3, b0), ...].

• cost (Union[Literal['euclidean', 'sq_euclidean', 'cosine', 'pnorm_p', 'sq_pnorm', 'elastic_l1', 'elastic_l2', 'elastic_stvs', 'elastic_sqk_overlap'], Mapping[Literal['xy', 'x', 'y'], Literal['euclidean', 'sq_euclidean', 'cosine', 'pnorm_p', 'sq_pnorm', 'elastic_l1', 'elastic_l2', 'elastic_stvs', 'elastic_sqk_overlap']]]) –

  Cost function to use. Valid options are:

  • str - name of the cost function for all terms, see get_available_costs().

  • dict - a dictionary with the following keys and values:

    • 'xy' - cost function for the linear term.

    • 'x' - cost function for the source quadratic term.

    • 'y' - cost function for the target quadratic term.

• cost_kwargs (Union[Mapping[str, Any], Mapping[Literal['x', 'y', 'xy'], Mapping[str, Any]]]) – Keyword arguments for the BaseCost or any backend-specific cost.

• a (Union[bool, str, None]) –

  Source marginals. Valid options are:

  • str - key in obs where the source marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - uniform marginals.

• b (Union[bool, str, None]) –

  Target marginals. Valid options are:

  • str - key in obs where the target marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - uniform marginals.

• kwargs (Any) – Keyword arguments for prepare().

Return type:

GWProblem[TypeVar(K, bound= Hashable), TypeVar(B, bound= OTProblem)]

Returns:

: Returns self and updates the following fields:

• problems - the prepared subproblems.

• solutions - set to an empty dict.

• batch_key - key in obs where batches are stored.

• stage - set to 'prepared'.

• problem_kind - set to 'quadratic'.